© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34655
    Prev
    Next
    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /portfolio
    -0.06
    æĥ¶
    -0.06
     appunto
    -0.06
    âĢ¦
    -0.06
    âģ
    -0.06
    luv
    -0.06
    ק×ķת
    -0.06
    çªĥ
    -0.05
    以åıĬ缸åħ³
    -0.05
    евиÑĩ
    -0.05
    POSITIVE LOGITS
    bez
    0.08
    à¹Ģà¸ģร
    0.08
    iggio
    0.08
    teurs
    0.08
    upe
    0.08
    大å§IJ
    0.08
    Liefer
    0.07
    ç¥ŀ级
    0.07
    ears
    0.07
    cntl
    0.07
    Activations Density 0.135%

    No Known Activations